ValueError: Variable E_conv0/w/Adam/ does not exist, or was not created with tf.get_variable()._valueerror: variable embedding does not exist, or -优快云博客

本文介绍了一种常见的TensorFlow编程错误，即在使用tf.train.AdamOptimizer进行优化时遇到的变量作用范围问题，并提供了具体的解决方案。通过在encoder函数中正确设置变量作用域，可以避免因变量未正确定义而导致的错误。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

运行tf.train.AdamOptimizer()函数,例如下面代码:

 self.EG_optimizer = tf.train.AdamOptimizer(
            learning_rate=EG_learning_rate,
            beta1=beta1
        ).minimize(
            loss=self.loss_EG,
            global_step=self.EG_global_step,
            var_list=self.E_variables + self.G_variables
        )

出现错误:

ValueError: Variable E_conv0/w/Adam/ does not exist, or was not created with tf.get_variable(). Did you mean to set reuse=None in VarScope?

解决方法:

在函数第一行添加:

with tf.variable_scope("encoder") as scope:

例如原encoder()函数代码为:

def encoder(self, image, reuse_variables=False):
       
        if reuse_variables:
            tf.get_variable_scope().reuse_variables()
        num_layers = int(np.log2(self.size_image)) - int(self.size_kernel / 2)
        current = image
        # conv layers with stride 2
        for i in range(num_layers):
            name = 'E_conv' + str(i)
            current = conv2d(
                    input_map=current,
                    num_output_channels=self.num_encoder_channels * (2 ** i),
                    size_kernel=self.size_kernel,
                    name=name
                )
            current = tf.nn.relu(current)

        # fully connection layer
        name = 'E_fc'
        current = fc(
            input_vector=tf.reshape(current, [self.size_batch, -1]),
            num_output_length=self.num_z_channels,
            name=name
        )

        # output
        return tf.nn.tanh(current)

修改后为:

  def encoder(self, image, reuse_variables=False):
        with tf.variable_scope("encoder") as scope:
            if reuse_variables:
                tf.get_variable_scope().reuse_variables()
            num_layers = int(np.log2(self.size_image)) - int(self.size_kernel / 2)
            current = image
            # conv layers with stride 2
            for i in range(num_layers):
                name = 'E_conv' + str(i)
                current = conv2d(
                        input_map=current,
                        num_output_channels=self.num_encoder_channels * (2 ** i),
                        size_kernel=self.size_kernel,
                        name=name
                    )
                current = tf.nn.relu(current)

            # fully connection layer
            name = 'E_fc'
            current = fc(
                input_vector=tf.reshape(current, [self.size_batch, -1]),
                num_output_length=self.num_z_channels,
                name=name
            )

            # output
            return tf.nn.tanh(current)